The article describes a multi-sensor dataset of human-humanhandovers composed of over 1000 recordings collected from18 volunteers. The recordings refer to 76 test configurations, whichconsider different volunteer's starting positions and roles, objectsto pass and motion strategies. In all experiments, we acquire 6-axisinertial data from two smartwatches, the 15-joint skeleton modelof one volunteer with an RGB-D camera and the upper-body modelof both persons using a total of 20 motion capture markers. Therecordings are annotated with videos and questionnaires about theperceived characteristics of the handover.

A multi-sensor dataset for human-human handover

Alessandro Carfì;Barbara Bruno;Fulvio Mastrogiovanni
2019-01-01

Abstract

The article describes a multi-sensor dataset of human-humanhandovers composed of over 1000 recordings collected from18 volunteers. The recordings refer to 76 test configurations, whichconsider different volunteer's starting positions and roles, objectsto pass and motion strategies. In all experiments, we acquire 6-axisinertial data from two smartwatches, the 15-joint skeleton modelof one volunteer with an RGB-D camera and the upper-body modelof both persons using a total of 20 motion capture markers. Therecordings are annotated with videos and questionnaires about theperceived characteristics of the handover.
File in questo prodotto:
File Dimensione Formato  
Carfi et al 2019.pdf

accesso aperto

Tipologia: Documento in versione editoriale
Dimensione 338.3 kB
Formato Adobe PDF
338.3 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11567/944100
Citazioni
  • ???jsp.display-item.citation.pmc??? 2
  • Scopus 21
  • ???jsp.display-item.citation.isi??? 16
social impact